CN113226010B - Implement agronomic test using spatial statistical model - Google Patents

Abstract

Disclosed herein are systems and methods for using spatial statistical models to maximize the efficacy of performing assays on agricultural fields. In one embodiment, a system receives first yield data for a first portion of an agronomic field that has received a first treatment and receives second yield data for a second portion of the agronomic field that has received a second treatment that is different from the first treatment. The system uses the spatial statistical model and the first yield data to calculate a yield value for the second portion of the agronomic field that indicates an agronomic yield for the second portion of the agronomic field if the second portion of the agronomic field received the first treatment but not the second treatment. Based on the calculated yield value and the second yield data, the system selects a second process. In one embodiment, in response to selecting the second process, the system generates a prescription map that includes the second process. The system may also generate one or more scripts that, when executed by the application controller, cause the application controller to control the operating parameters of the agricultural implement to apply the second process.

Description

Implement agronomic test using spatial statistical model

Copyright description

A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the patent and trademark office patent file or records, but otherwise reserves all copyright rights whatsoever.2015-2019 Craimidt (The Climate Corporation).

Technical Field

One technical field of the present disclosure is digital computer modeling of agricultural fields. In particular, the present disclosure relates to identifying locations for achieving specific practices in an agricultural field and having agricultural implements perform specific practices in the agricultural field.

Background

The approaches described in this section are approaches that could be pursued, but not necessarily approaches that have been previously conceived or pursued. Thus, unless otherwise indicated, any approaches described in this section are not to be construed so as to qualify as prior art merely by virtue of their inclusion in this section.

Farmers are faced with making a variety of decisions regarding the management of agricultural fields. These decisions encompass determining what crop is planted, what seed is planted for the crop, when the crop is harvested, whether cultivation is performed, irrigation, application of pesticides including fungicides and herbicides, and application of fertilizers, and what type of pesticide or fertilizer is applied.

Often, improvements in field management practices can be made by using different hybrid seeds or different seed varieties, applying different products to the field, or performing different management activities on the field. These improvements may not be readily identifiable to farmers who work with only information about their own fields. Furthermore, even if better practices are known, farmers may not be able to determine whether new practices are beneficial over previous practices.

To determine whether the new practice produces better results than the previous practices, farmers may use portions of the agricultural field for testing, where one or more portions of the agricultural field receive different management practices than other portions of the agricultural field. By conducting tests on portions of the agricultural field, farmers can continue to utilize the agricultural field in a previously effective manner while testing different practices to determine if they would result in improved results.

One problem with achieving trials on agronomic fields is that it is not always clear whether the perceived benefit or harm of the trial is an actual benefit or harm, field level anomalies or statistical anomalies. This problem is compounded when different treatments are expected to have only a small effect on yield in an agronomic field. One reason for this problem is that the results of agronomic tests are often compared to yields in the vicinity or in previous years, both of which may differ from the yields at the test site for reasons other than treatment differences.

Another problem with achieving these tests is that it is not always clear to the farmer where it is best to place the test sites for the most efficient use of the agricultural field. Some regions may have greater congenital differences such that the variation in yield is not statistically significant in other locations. Thus, farmer's test practices may occupy a large portion of the field in the strip test to produce a set of results that could otherwise be produced with the same level of statistical significance with a smaller portion of the agricultural field.

Thus, there is a need for a system that utilizes field data to identify test locations for implementing trials. In addition, there is a need for a system that: the system uses the field data to determine whether the effect of the trial is significant enough to justify a change to the management program in other parts of the field.

Disclosure of Invention

The appended claims may serve as an inventive content of the present disclosure.

Drawings

In the drawings:

FIG. 1 illustrates an example computer system configured to perform the functions described herein, which is shown in a field environment along with other devices with which the system may interoperate.

FIG. 2 illustrates two views of an example logical organization of an instruction set in main memory when an example mobile application is loaded for execution.

FIG. 3 illustrates a programmed process by which an agricultural intelligence computer system generates one or more preconfigured agricultural models using agricultural data provided by one or more data sources.

FIG. 4 is a block diagram that illustrates a computer system upon which an embodiment of the invention may be implemented.

FIG. 5 depicts an example embodiment of a timeline view of data entries.

FIG. 6 depicts an example embodiment of a spreadsheet view of a data entry.

FIG. 7 depicts a method for inferring control data for an agronomic test using a spatial statistical model.

FIG. 8 depicts a method for selecting a location for performing an experiment using a spatial statistical model.

Detailed Description

In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. It will be apparent, however, that the embodiments may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the present disclosure. Embodiments are disclosed in the sections according to the following outline:

1. General overview

2. Example agricultural Intelligent computer System

2.1. Structural overview

2.2. Overview of application programs

2.3. Data ingestion by a computer system

2.4. Process overview-agronomic model training

2.5. Implementation example-hardware overview

3. Generating inferred controls using spatial modeling

3.1. Received data

3.2. Statistical model

3.3. Determining test impact

3.4. Practical application of statistical model

4. Using spatial modeling to identify trial positions

4.1. Statistical model

4.2. Selecting a portion of an agronomic field

4.3. Practical application of location identification

5. Benefits of certain embodiments

6. Expansion and alternatives

*

1. General overview

Systems and methods for utilizing spatial statistical models as part of the actual implementation of agronomic tests on an agronomic field are described herein. According to one embodiment, an agricultural intelligence computer system generates a spatial statistical model based on yield data for a portion of an agricultural field receiving a first process, and calculates a yield value for a location receiving a second process using the spatial statistical model. The calculated yield value may then be compared to yield data for the location where the second process was received to determine whether the second process has a beneficial or detrimental effect over the first process. If the second process is deemed more beneficial than the first process, the system may then generate a prescription map that implements the second process. The spatial statistical model may additionally be used to identify a location on the agronomic field where the spatial statistical model is most effective and generate a prescription map of the trial included in the identified location.

In one embodiment, a method includes: receiving first yield data for a first portion of an agronomic field, the first portion of the agronomic field having received a first treatment; receiving second yield data for a second portion of the agricultural field that has received a second treatment different from the first treatment; calculating, using the spatial statistical model and the first yield data, a yield value for the second portion of the agronomic field, the yield value indicating an agronomic yield for the second portion of the agronomic field if the second portion of the agronomic field has received the first treatment but not the second treatment; selecting a second process based on the calculated yield value and the second yield data; in response to selecting the second process, generating a prescription map, the prescription map including the second process; one or more scripts are generated that, when executed by the application controller, cause the application controller to control the operating parameters of the agricultural implement to apply the second process.

In one embodiment, a method includes: receiving yield data for an agronomic field, the agronomic field having received a first treatment; for each particular portion of the plurality of particular portions of the agronomic field, performing: calculating a yield value for a particular portion of the agronomic field using the spatial statistical model and yield data for individual portions of the agronomic field; and calculating an average statistical deviation value for the particular portion of the agronomic field using the yield value and the portion of the yield data corresponding to the particular portion of the agronomic field; selecting one or more of the plurality of specific sections of the agricultural field as a test section of the agricultural field based on the average statistical deviation value for each of the plurality of specific sections of the agricultural field; in response to selecting the test portion of the agronomic field, generating a prescription map including a second process in the test portion that is different from the first process; one or more scripts are generated that, when executed by the application controller, cause the application controller to control the operating parameters of the agricultural implement to apply the second treatment to the test portion of the agronomic field.

2. Example agricultural Intelligent computer System

2.1 structural overview

FIG. 1 is an example computer system configured to perform the functions described herein, the example computer system being shown in a field environment with other devices with which the system may interoperate. In one embodiment, the user 102 owns, operates, or otherwise governs a field manager computing device 104 in or associated with a field location, such as a field intended for agricultural activity or a management location for one or more agricultural fields. The field manager computer device 104 is programmed or configured to provide field data 106 to the agricultural intelligent computer system 130 via one or more networks 109.

Examples of field data 106 include (a) identification data (e.g., planting area, field name, field identifier, geographic identifier, boundary identifier, crop identifier, and any other suitable data that may be used to identify farm land, such as public land units (CLU), land and plot numbers, land numbers, geographic coordinates and boundaries, farm Serial Numbers (FSN), farm numbers, land zone numbers, field numbers, regions, towns, and/or ranges), (b) harvest data (e.g., crop type, crop variety, crop rotation, whether crops are organically planted, harvest date, actual Production History (APH), expected yield, crop price, crop income, cereal moisture, farming practices, and previous growth season information), (c) soil data (e.g., type, composition, pH, organic Matter (OM), cation Exchange Capacity (CEC)), (d) planting data (e.g., planting date, seed type(s), relative Maturity (RM) of planted seed(s), (e) seed(s), fertilizer data (e.g., seed (CEC))); nutrient type (nitrogen, phosphorus, potassium), type of application, date of application, amount, source, method of application), (f) chemical application data (e.g., pesticides, herbicides, fungicides, other substances or substance mixtures intended for use as plant regulators, defoliants, or desiccants, application dates, amount, source, method), (g) irrigation data (e.g., date of application, amount, source, method), (h) weather data (e.g., precipitation, rate of rainfall, predicted rainfall, water runoff rate area, temperature, wind, forecast, pressure, visibility, cloud, thermal index, dew point, humidity, snow depth, air quality, sunrise, sunset), (i) image data (e.g., images and spectral information from agricultural device sensors, cameras, computers, smart phones, tablets, unmanned aerial vehicles, aircraft, or satellites; (j) Scout observations (photographs, videos, free form notes, voice recordings, voice transcription, weather conditions (temperature, precipitation (current and long term), soil moisture, crop growth stage, wind speed, relative humidity, dew point, black layer)), and (k) soil, seeds, crop weather, pest reports, and prediction sources and databases.

The data server computer 108 is communicatively coupled to the agricultural intelligent computer system 130 and is programmed or configured to send external data 110 to the agricultural intelligent computer system 130 via the network(s) 109. The external data server computer 108 may be owned or operated by the same legal or entity as the agricultural intelligent computer system 130, or by a different person or entity such as a government agency, non-government organization (NGO), and/or a private data service provider. Examples of external data include weather data, image data, soil data, or statistical data related to crop yield, etc. The external data 110 may be composed of the same type of information as the field data 106. In some embodiments, the external data 110 is provided by an external data server 108 owned by the same entity that owns and/or operates the agricultural intelligent computer system 130. For example, agricultural intelligent computer system 130 may include a data server dedicated to focusing on the type of data (such as weather data) that may otherwise be obtained from a third party source. In some embodiments, the external data server 108 may actually be incorporated within the system 130.

Agricultural device 111 may have one or more remote sensors 112 secured thereto that are communicatively coupled directly or indirectly to agricultural intelligent computer system 130 via agricultural device 111 and programmed or configured to send sensor data to agricultural intelligent computer system 130. Examples of agricultural devices 111 include tractors, combine harvesters, sowers, trucks, fertilizing equipment, aircraft including unmanned aircraft, and physical machines or hardware, typically mobile machines, and any other item that may be used for tasks associated with agriculture. In some embodiments, a single unit of device 111 may include multiple sensors 112 coupled locally in a network on the device; a Controller Area Network (CAN) is an example of such a network that may be installed in combine harvesters, sprayers, and cultivator. The application controller 114 is communicatively coupled to the agricultural intelligent computer system 130 via the network(s) 109 and is programmed or configured to receive one or more scripts from the agricultural intelligent computer system 130 that are used to control the operating parameters of the agricultural vehicle or implement. For example, a Controller Area Network (CAN) bus interface may be used to support communications from the agricultural intelligent computer system 130 to the agricultural device 111, such as how CLIMATE FIELDVIEW DRIVE available from claimatt corporation of san francisco, california is used. The sensor data may consist of the same type of information as the field data 106. In some embodiments, the remote sensor 112 may not be fixed to the agricultural device 111, but may be remotely located in the field and may be in communication with the network 109.

The apparatus 111 may include a cab computer 115 programmed with a cab application, which may include versions or variants of mobile applications for the device 104, which are further described in other sections herein. In one embodiment, the cab computer 115 comprises a compact computer, typically a tablet-sized computer or smart phone, having a graphical screen display (such as a color display) mounted within the operator cab of the device 111. The cab computer 115 may implement some or all of the operations and functions further described herein with respect to the mobile computer device 104.

Network(s) 109 broadly represent any combination of one or more data communication networks including a local area network, a wide area network, an interconnection network, or the internet, using any of wired or wireless links including terrestrial links or satellite links. The network(s) may be implemented by any medium or mechanism that provides for the exchange of data between the various elements of fig. 1. The various elements of fig. 1 may also have direct (wired or wireless) communication links. The sensors 112, controller 114, external data server computer 108, and other elements of the system each include interfaces compatible with the network(s) 109 and are programmed or configured to communicate across the network using standardized protocols (such as TCP/IP, bluetooth, CAN protocols, and higher layer protocols such as HTTP, TLS, etc.).

Agricultural intelligent computer system 130 is programmed or configured to receive field data 106 from field manager computing device 104, external data 110 from external data server computer 108, and sensor data from remote sensor 112. Agricultural intelligence computer system 130 can also be configured to host, use or execute one or more computer programs, other software elements, digitally programmed logic (such as an FPGA or ASIC), or any combination thereof to perform the conversion and storage of data values, the creation of digital models of one or more crops on one or more farms, the generation of suggestions and notifications, and the generation of scripts and the transmission of scripts to application controller 114 in a manner further described in other sections of this disclosure.

In one embodiment, agricultural intelligent computer system 130 is programmed with or includes a communications layer 132, a presentation layer 134, a data management layer 140, a hardware/virtualization layer 150, and a model and field data repository 160. In this context, "layer" refers to any combination of electronic digital interface circuitry, microcontrollers, firmware such as drivers, and/or computer programs or other software elements.

The communication layer 132 may be programmed or configured to perform input/output interface functions including sending requests for field data, external data, and sensor data to the field manager computing device 104, the external data server computer 108, and the remote sensor 112, respectively. The communication layer 132 may be programmed or configured to send the received data to the model and field data repository 160 for storage as field data 106.

The presentation layer 134 may be programmed or configured to generate a Graphical User Interface (GUI) to be displayed on the field manager computing device 104, the cab computer 115, or other computer coupled to the system 130 via the network 109. The GUI may include controls for entering data to be sent to the agricultural intelligent computer system 130, generating requests for models and/or advice, and/or displaying advice, notifications, models, prescription maps, and other field data.

The data management layer 140 may be programmed or configured to manage read and write operations involving the repository 160 and other functional elements of the system, including queries and result sets that are communicated between the functional elements of the system and the repository. Examples of the data management layer 140 include JDBC, SQL server interface code, and/or HADOOP interface code, among others. Repository 160 may include a database. As used herein, the term "database" may refer to a data volume, a relational database management system (RDBMS), or both. As used herein, a database may include any collection of data, including hierarchical databases, relational databases, flat file databases, object-relational databases, object-oriented databases, distributed databases, and any other structured collection of records or data stored in a computer system. Examples of RDBMS include, but are not limited to MYSQL、/>SERVER、/>And a posttgresql database. However, any database supporting the systems and methods described herein may be used.

When field data 106 is not provided directly to the agricultural intelligent computer system via one or more agricultural machines or agricultural machine devices that interact with the agricultural intelligent computer system, the user may be prompted to enter such information via one or more user interfaces on the user devices (served by the agricultural intelligent computer system). In an example embodiment, a user may specify identification data by accessing a map on a user device (served by an agricultural intelligent computer system) and selecting a particular CLU that has been graphically shown on the map. In an alternative embodiment, user 102 may specify the identification data by accessing a map on a user device (served by agricultural intelligent computer system 130) and drawing a field boundary over the map. Such CLU selections or mapping represent geographic identifiers. In an alternative embodiment, the user may specify identification data by accessing field identification data (provided in a shape file or similar format) from the United states department of agricultural farm service or other source via the user device, and providing such field identification data to the agricultural intelligent computer system.

In an example embodiment, agricultural intelligent computer system 130 is programmed to generate and cause display of a graphical user interface that includes a data manager for data entry. After one or more fields have been identified using the methods described above, the data manager may provide one or more graphical user interface widgets that, when selected, may identify changes to fields, soil, crops, farming, or nutrient practices. The data manager may include a timeline view, a spreadsheet view, and/or one or more editable programs.

FIG. 5 depicts an example embodiment of a timeline view of data entries. Using the display depicted in fig. 5, the user computer can enter a selection of a particular field and a particular date for event addition. Events described at the top of the timeline may include nitrogen, planting, practice, and soil. To add a nitrogen administration event, the user computer may provide input to select a nitrogen tag. The user computer may then select a location on the timeline for a particular field to indicate nitrogen application on the selected field. In response to receiving a selection of a location on the timeline for a particular field, the data manager may display a data entry overlay, allowing the user computer to enter data regarding nitrogen application, planting process, soil application, farming procedure, irrigation practices, or other information related to the particular field. For example, if the user computer selects a portion of the timeline and indicates nitrogen application, the data entry overlay may include a field for entering the amount of nitrogen applied, the date of application, the type of fertilizer used, and any other information related to nitrogen application.

In one embodiment, a data manager provides an interface for creating one or more programs. In this context, "program" refers to a collection of data about nitrogen application, planting process, soil application, farming process, irrigation practices, or other information that may be relevant to one or more fields, which may be stored in a digital data storage device for reuse as a collection in other operations. After a program has been created, it can be conceptually applied to one or more fields, and a reference to the program can be stored in digital storage in association with data identifying those fields. Thus, instead of manually entering exactly the same data regarding the same nitrogen application for a plurality of different fields, the user computer may create a program indicating a specific application of nitrogen and then apply the program to the plurality of different fields. For example, in the timeline view of FIG. 5, the top two timelines select a "spring application" program that includes 150 pounds of nitrogen per acre (150 lbs N/ac) at the beginning of April. The data manager may provide an interface for editing the program. In one embodiment, when a particular program is edited, each field for which the particular program has been selected is edited. For example, in fig. 5, if the "spring application" program is edited to reduce nitrogen application to 130 pounds of nitrogen per acre, the top two fields may be updated to have reduced nitrogen application based on the edited program.

In one embodiment, in response to receiving an edit to a field for which a program has been selected, the data manager removes the field from correspondence with the selected program. For example, if nitrogen application is added to the top field of fig. 5, the interface may be updated to indicate that the "spring application" program is no longer being applied to the top field. Although nitrogen administration may remain in the early four months, the renewal of the "spring administration" program does not alter nitrogen administration in four months.

FIG. 6 depicts an example embodiment of a spreadsheet view of a data entry. Using the display depicted in fig. 6, a user can create and edit information for one or more fields. As depicted in fig. 6, the data manager may include a spreadsheet for entering information about nitrogen, planting, practice, and soil. To edit a particular entry, the user computer may select a particular entry in the spreadsheet and update the value. For example, fig. 6 depicts an ongoing update of the target yield value for the second field. In addition, the user computer may select one or more fields to apply one or more programs. In response to receiving a program selection for a particular field, the data manager may automatically complete an entry for the particular field based on the selected program. As with the timeline view, in response to receiving an update to a particular program, the data manager may update an entry for each field associated with the program. In addition, in response to receiving an edit to one of the entries for the farm, the data manager may remove the selected program from correspondence with the farm.

In one embodiment, the model and field data is stored in a model and field data repository 160. The model data includes data models created for one or more fields. For example, the crop model may include a digitally-constructed model of crop development on one or more fields. In this context, a "model" refers to a collection of electronically digital stores of executable instructions and data values associated with each other that are capable of receiving a call, or parse request for a program or other number and responding to the call, or parse request for the program or other number based on specified input values to produce one or more stored or calculated output values that may serve as a basis for computer-implemented advice, output data display, or machine control, among others. Those skilled in the art find it convenient to express a model using mathematical equations, but such expression does not limit the model disclosed herein to abstract concepts; rather, each model herein has practical application in a computer in the form of stored executable instructions and data that use the computer to implement the model. The model may include a model of past events on one or more fields, a model of the current state of one or more fields, and/or a model of predicted events for one or more fields. The model and field data may be stored in data structures in memory, in rows in a database table, in a flat file or spreadsheet, or in other forms of stored digital data.

In one embodiment, each of the spatial statistical modeling instructions 136, the process selection instructions 137, and the location selection instructions 138 comprise a set of one or more pages of main memory (such as RAM) in the agricultural intelligent computer system 130 into which executable instructions have been loaded, and which when executed cause the agricultural intelligent computer system to perform the functions or operations described herein with reference to those modules. For example, the spatial statistical modeling instructions 136 may include a set of pages in RAM that contain instructions that, when executed, cause the spatial statistical modeling functions described herein. The instructions may be in machine executable code in the instruction set of the CPU and may be compiled based on source code written in JAVA, C, c++, object-C, or any other human-readable programming language or environment, alone or in combination with scripts in JAVASCRIPT, other scripting languages, and other programming source text. The term "page" is intended to refer broadly to any region within main memory, and the particular terms used in a system may vary depending on the memory architecture or processor architecture. In another embodiment, each of the spatial statistical modeling instructions 136 may also represent one or more files or items of source code that are digitally stored in a mass storage device, such as non-volatile RAM or disk storage, in the agricultural intelligent computer system 130 or a separate repository system, which when compiled or interpreted, cause the agricultural intelligent computer system to perform the functions or operations described herein with reference to those modules, when executed. In other words, the figures may represent the manner in which a programmer or software developer organizes and arranges source code for later compilation into an executable file, or interpretation into byte code or equivalent for execution by agricultural intelligent computer system 130.

The spatial statistical modeling instructions 136 include a set of computer readable instructions that, when executed by the one or more processors, cause the agricultural intelligent computer system to generate a spatial statistical model of the yield for use in generating control data for an agronomic test and/or in identifying locations for achieving the test. The process selection instructions 137 include a set of computer-readable instructions that, when executed by the one or more processors, cause the agricultural intelligent computer system to select a particular process based on the spatial statistical model of yield and yield for one or more test locations on the farm that receive a process different from the rest of the agricultural farm. The location selection instructions 138 include a set of computer-readable instructions that, when executed by the one or more processors, cause the agricultural intelligent computer system to select a location for implementing the test based on the spatial statistical model of yield and yield data for the agronomic field.

The hardware/virtualization layer 150 includes one or more Central Processing Units (CPUs), memory controllers, and other devices, components, or elements of a computer system, such as volatile or non-volatile memory, non-volatile storage such as magnetic disks, and I/O devices or interfaces such as those illustrated and described in connection with fig. 4. Layer 150 may also include programmed instructions configured to support virtualization, containerization, or other techniques.

For purposes of illustrating a clear example, fig. 1 shows a limited number of examples of certain functional elements. However, in other embodiments, there may be any number of such elements. For example, embodiments may use thousands or millions of different mobile computing devices 104 associated with different users. Further, the system 130 and/or the external data server computer 108 may be implemented using two or more processors, cores, clusters, or instances of physical or virtual machines, configured in discrete locations or co-located with other elements in a data center, shared computing facility, or cloud computing facility.

2.2. Overview of application programs

In one embodiment, an implementation of the functionality described herein using one or more computer programs or other software elements loaded into and executed using one or more general-purpose computers will result in the general-purpose computer being configured as a particular machine or computer specifically adapted to perform the functionality described herein. Moreover, each of the flowcharts further described herein may function as an algorithm, plan, or direction, alone or in combination with the description of the processes and functions described herein, which may be used to program a computer or logic to implement the described functions. In other words, all the prosecution text and all the drawings herein are together intended to provide an algorithmic, planned or directional disclosure in combination with the skills and knowledge of a person having a skill level appropriate to such inventions and disclosures, which disclosure is sufficient to allow a skilled person to program a computer to perform the functions described herein.

In one embodiment, user 102 interacts with agricultural intelligent computer system 130 using field manager computing device 104 configured with an operating system and one or more applications or apps; the field manager computing device 104 may also be independently and automatically interoperable with the agricultural intelligent computer system under program control or logic control, and does not always require direct user interaction. The field manager computing device 104 broadly represents one or more of a smart phone, PDA, tablet computing device, laptop computer, desktop computer, workstation, or any other computing device capable of transmitting and receiving information and performing the functions described herein. The field manager computing device 104 may communicate via a network using a mobile application stored on the field manager computing device 104, and in some embodiments, the device may be coupled to the sensor 112 and/or the controller 114 using a cable 113 or connector. The user 102 may own, operate, or otherwise manage and use more than one field manager computing device 104 at a time in connection with the system 130.

The mobile application may provide client-side functionality to one or more mobile computing devices via a network. In one example embodiment, the field manager computing device 104 may access the mobile application via a web browser or a local client application or app. The farm manager computing device 104 can transmit and receive data to and from one or more front-end servers using a network-based protocol or format (such as HTTP, XML, and/or JSON) or app-specific protocol. In one example embodiment, the data may take the form of requests and user information inputs (such as field data) into the mobile computing device. In some embodiments, the mobile application interacts with location tracking hardware and software on the field manager computing device 104 that uses standard tracking techniques such as multi-edge positioning of radio signals, global Positioning System (GPS), wiFi positioning system, or other mobile positioning methods to determine the location of the field manager computing device 104. In some cases, location data or other data associated with the device 104, the user 102, and/or the user account(s) may be obtained by querying the operating system of the device or requesting an app on the device to obtain the data from the operating system.

In one embodiment, field manager computing device 104 sends field data 106 to agricultural intelligent computer system 130, field data 106 including or including, but not limited to, data values representing one or more of: the method includes determining a geographic location of one or more fields, cultivation information of one or more fields, crops planted in one or more fields, and soil data extracted from one or more fields. The field manager computing device 104 may send the field data 106 in response to user input from the user 102, the user input 102 specifying data values for one or more fields. Additionally, the field manager computing device 104 can automatically send the field data 106 when one or more of the data values become available to the field manager computing device 104. For example, the field manager computing device 104 may be communicatively coupled to remote sensors 112 and/or application controllers 114, including irrigation sensors and/or irrigation controllers. In response to receiving data indicating that application controller 114 is draining to one or more fields, field manager computing device 104 can send field data 106 to agricultural intelligent computer system 130, field data 106 indicating that water has been drained on one or more fields. The field data 106 identified in this disclosure may be entered and transmitted using electronic digital data that is transmitted between computing devices using a parameterized URL over HTTP or another suitable communication or messaging protocol.

A commercial example of a mobile application is CLIMATE FIELDVIEW, commercially available from claimatt corporation of san francisco, california. The CLIMATE FIELDVIEW application or other application may be modified, extended, or adapted to include features, functions, and programming that have not been disclosed prior to the filing date of the present disclosure. In one embodiment, the mobile application includes an integrated software platform that allows the grower to make fact-based decisions about his operation because the platform combines historical data about the grower's field with any other data that the grower wishes to compare. The combining and comparing may be performed in real time and based on a scientific model that provides a potential scenario to allow the grower to make better, more informed decisions.

FIG. 2 illustrates two views of an example logical organization of an instruction set in main memory when an example mobile application is loaded for execution. In fig. 2, each named element represents an area of one or more pages of RAM or other main memory or an area of one or more blocks of disk storage or other non-volatile storage, as well as programmed instructions within those areas. In one embodiment, in view (a), the mobile computer application 200 includes an account field data ingestion sharing instruction 202, an overview and alert instruction 204, a digital map book instruction 206, a seed and planting instruction 208, a nitrogen instruction 210, a weather instruction 212, a field health instruction 214, and a performance instruction 216.

In one embodiment, the mobile computer application 200 includes account, farm, data ingestion, sharing instructions 202 programmed to receive, convert, and ingest farm data from a third party system via a manual upload or API. The data types may include field boundaries, yield maps, planting maps, soil test results, application maps, and/or management zones, etc. The data formats may include shape files, local data formats of third parties, and/or Farm Management Information System (FMIS) export, among others. Receiving the data may occur via a manual upload, an email with an attachment, an external API pushing the data to the mobile application, or an instruction to call an API of an external system to pull the data into the mobile application. In one embodiment, the mobile computer application 200 includes a data inbox. In response to receiving a selection of the data inbox, the mobile computer application 200 may display a graphical user interface for manually uploading data files and importing the uploaded files into the data manager.

In one embodiment, the digital map book instructions 206 include a field map data layer stored in device memory and are programmed with data visualization tools and geospatial field annotations. This provides the grower with convenient information available to the tentacle for reference, logging, and visual insight into field performance. In one embodiment, the summary and alert instructions 204 are programmed to provide an operational scope view of what is important to the grower, and to provide timely advice to take action or focus on a particular problem. This allows the grower to focus on where attention is needed to save time and maintain yield throughout the season. In one embodiment, the seed and planting instructions 208 are programmed to provide tools for seed selection, hybridization placement, and script creation (including Variable Rate (VR) script creation) based on scientific models and empirical data. This enables the grower to maximize yield or return on investment through optimized seed purchase, placement and population.

In one embodiment, script generation instructions 205 are programmed to provide an interface for generating a script comprising a Variable Rate (VR) fertility script. The interface enables the grower to create scripts for field implements such as nutrient application, planting, and irrigation. For example, the planting script interface may include a tool for identifying a seed type for planting. In response to receiving the selection of the seed type, the mobile computer application 200 may display one or more fields divided into management zones, such as a field map data layer created as part of the digital map book instructions 206. In one embodiment, the management zone includes soil zones and panels identifying each soil zone and soil names, textures, drainage or other field data for each zone. The mobile computer application 200 may also display tools for editing or creating such tools, such as graphical tools for drawing management zones (such as soil zones), on top of a map of one or more fields. The planting process may be applied to all of the management zones, or different planting processes may be applied to different subsets of the management zones. When a script is created, the mobile computer application 200 may make the script available in a format readable by the application controller (such as an archive or compressed format). Additionally and/or alternatively, scripts may be sent from mobile computer application 200 directly to cab computer 115 and/or uploaded to one or more data servers and stored for future use.

In one embodiment, the nitrogen instructions 210 are programmed to provide a tool to inform nitrogen decisions by visualizing availability of nitrogen to crops. This enables the grower to maximize yield or return on investment through optimized nitrogen application during the season. Example programmed functions include displaying an image (such as a SSURGO image) to enable mapping of fertilizer application zones and/or images generated from sub-field soil data (such as data obtained from sensors) at high spatial resolution (fine to millimeters or less depending on the proximity and resolution of the sensors); uploading the zone defined by the existing grower; providing a chart of plant nutrient availability and/or a map enabling adjustment of nitrogen application(s) across multiple zones; outputting a script to drive the machine; tools for massive data entry and adjustment; and/or maps for data visualization, etc. In this context, "mass data entry" may mean entering data once and then applying the same data to a plurality of fields and/or zones defined in the system; example data may include nitrogen application data that is the same for many fields and/or zones of the same planter, but such mass data entry is suitable for entering any type of field data into the mobile computer application 200. For example, the nitrogen instructions 210 may be programmed to accept definitions of nitrogen application programs and nitrogen practice programs, and to accept user input specifying those programs to be applied across multiple fields. In this context, "nitrogen administration program" refers to a named set of stored data that correlates to: a name, color code or other identifier, one or more application dates, the type of material or product used for each of the dates and amounts, the method of application or incorporation (such as injection or scattering), and/or the amount or rate of application for each of the dates, the crop or hybridization being the subject of application, etc. In this context, "nitrogen practice" refers to a named set of stored data that is associated with: practice names; a prior crop; a farming system; a main cultivation date; one or more previous farming systems that were used; one or more indicators of the type of application used, such as organic fertilizer. The nitrogen instructions 210 may also be programmed to generate and cause display of a nitrogen map indicating a plan of use of the specified nitrogen by the plant and whether surplus or shortage is predicted; for example, in some embodiments, different color indicators may flag the magnitude of the surplus or the magnitude of the shortage. In one embodiment, the nitrogen map comprises a graphical display in a computer display device, comprising: a plurality of rows, each row associated with a field and identifying the field; data specifying a graphical representation of what crops are planted in a field, field size, field location, and field perimeter; in each row, a monthly timeline with graphical indicators specifying each nitrogen application and quantity at points associated with month names; and a surplus or shortage indicator of numbers and/or colors, wherein the colors indicate magnitudes.

In one embodiment, the nitrogen map may include one or more user input features (such as dials or sliders) to dynamically change the nitrogen planting and practice program so that the user may optimize his nitrogen map. The user may then implement one or more scripts, including Variable Rate (VR) fertility scripts, using their optimized nitrogen map and related nitrogen planting and practice programs. The nitrogen instructions 210 may also be programmed to generate and cause to be displayed a nitrogen map indicating a plan for use of the specified nitrogen by the plant and whether surplus or shortage is predicted; in some embodiments, the different colored indicators may mark the magnitude of the surplus or the magnitude of the shortage. Using a digital and/or colored surplus or shortage indicator, the nitrogen map may display a prediction of plant usage of the specified nitrogen, and whether surplus or shortage is predicted for different times in the past and future (such as daily, weekly, monthly or yearly), with the color indicating the magnitude. In one embodiment, the nitrogen map may include one or more user input features (such as dials or sliders) to dynamically change the nitrogen planting and practice program so that a user may optimize his nitrogen map, such as to obtain a preferred amount of surplus to shortage. The user may then implement one or more scripts, including Variable Rate (VR) fertility scripts, using their optimized nitrogen map and related nitrogen planting and practice programs. In other embodiments, instructions similar to nitrogen instructions 210 may be used for application of other nutrients (such as phosphorus and potassium), pesticide application, and irrigation procedures.

In one embodiment, the weather instructions 212 are programmed to provide field-specific recent weather data and forecasted weather information. This enables the grower to save time and have an integrated display that is decision-making efficient with respect to daily operability.

In one embodiment, the field health instructions 214 are programmed to provide timely telemetry images to highlight crop changes and potential problems for the season. Example programmed functions include: cloud inspection to identify possible clouds or cloud shadows; determining a nitrogen index based on the field image; graphically visualizing and viewing and/or sharing scout notes for scout layers, including, for example, layers related to field health; and/or downloading satellite images from multiple sources, and prioritizing images for growers, etc.

In one embodiment, the performance instructions 216 are programmed to provide reporting, analysis, and insight tools for evaluation, insight, and decision making using farm data. This enables growers to seek improved results in the next year through factual-based conclusions as to why return on investment was at a previous level and insight into yield limiting factors. Performance instructions 216 may be programmed to communicate via network(s) 109 to a back-end analysis program that is executed at agricultural intelligent computer system 130 and/or external data server computer 108 and that is configured to analyze metrics such as yield, yield differences, hybridization, populations, SSURGO zones, soil test properties, or elevation, etc. The programmed reports and analyses may include yield variability analysis, process impact estimation, benchmarking analysis for yield and other metrics for other growers based on anonymous data collected from many growers, or data for seeds and plants, etc.

Applications having instructions configured in this manner may be implemented for different computing device platforms while maintaining the same general user interface appearance. For example, a mobile application may be programmed for execution on a tablet, smart phone, or server computer accessed using a browser at a client computer. Further, a mobile application configured for use with a tablet computer or smart phone may provide a complete app experience or cab app experience suitable for display and processing capabilities of the cab computer 115. For example, referring now to view (b) of fig. 2, in one embodiment, the cab computer application 220 may include map cab instructions 222, remote view instructions 224, data collection and transfer instructions 226, machine alert instructions 228, script transfer instructions 230, and scout cab instructions 232. The code library of instructions for view (b) may be the same as for view (a), and the executable files implementing the code may be programmed to detect the type of platform on which these executable files are executing, and to expose only those functions that are suitable for the cab platform or full platform through the graphical user interface. This approach enables the system to identify distinct user experiences appropriate for the in-cab environment and the different technical environments of the cab. Map cab instructions 222 may be programmed to provide a map view of a field, farm, or area useful in directing machine operation. The remote viewing instructions 224 may be programmed to turn on, manage views of machine activities, and provide views of those machine activities in real time or near real time via a wireless network, wired connector or adapter, or other computing device connected to the system 130. The data collection and transfer instructions 226 may be programmed to initiate, manage, and provide for transfer of data collected at the sensors and controllers to the system 130 via a wireless network, wired connector or adapter, or the like. Machine alert instructions 228 may be programmed to detect operational problems with a machine or tool associated with the cab and generate an operator alert. Script transfer instructions 230 may be configured to be transferred in the form of instruction scripts configured to direct machine operations or data collection. The snoop cab instructions 232 may be programmed to: the location-based alarms and information received from the system 130 are displayed based on the location of the field manager computing device 104, the agricultural equipment 111, or the sensor 112 in the field, and the location-based scout observations are ingested, managed, and delivered to the system 130 based on the location of the agricultural equipment 111 or the sensor 112 in the field.

2.3. Data ingestion by a computer system

In one embodiment, the external data server computer 108 stores external data 110 including soil data representing soil composition for one or more fields and weather data representing temperature and precipitation on one or more fields. Weather data may include past and current weather data and forecasts of future weather data. In one embodiment, the external data server computer 108 includes multiple servers hosted by different entities. For example, a first server may contain soil composition data, while a second server may include weather data. In addition, soil composition data may be stored in a plurality of servers. For example, one server may store data representing percentages of sand, silt, and clay in the soil, while a second server may store data representing percentages of Organics (OM) in the soil.

In one embodiment, remote sensor 112 includes one or more sensors programmed or configured to generate one or more observations. The remote sensor 112 may be an air sensor such as a satellite, a vehicle sensor, a planting equipment sensor, a farming sensor, a fertilizer or pesticide application sensor, a harvester sensor, and any other implement capable of receiving data from one or more fields. In one embodiment, application controller 114 is programmed or configured to receive instructions from agricultural intelligent computer system 130. The application controller 114 may also be programmed or configured to control operating parameters of the agricultural vehicle or implement. For example, the application controller may be programmed or configured to control operating parameters of a vehicle (such as a tractor), planting equipment, farming equipment, fertilizer or pesticide equipment, harvester equipment, or other farm implement (such as a water valve). Other embodiments may use any combination of sensors and controllers, the following being merely selected examples thereof.

The system 130 may, under the control of the user 102, either mass-source or ingest data from a large number of growers that have contributed data to the shared database system. When one or more user-controlled computer operations are requested or triggered to obtain data for use by the system 130, such a form of obtaining data may be referred to as "manual data ingestion. For example, a CLIMATE FIELDVIEW application commercially available from claimatt corporation of san francisco, california may be operated to export data to system 130 for storage in repository 160.

For example, the seed monitor system may both control the planter assembly and obtain planting data, including signals from the seed sensors via a signal harness that includes a CAN backbone and point-to-point connections for registration and/or diagnostics. The seed monitor system may be programmed or configured to display seed spacing, population, and other information to the user via the cab computer 115 or other device within the system 130. Examples are disclosed in U.S. patent No. 8,738,243 and U.S. patent publication 20150094916, and the present disclosure assumes that those other patent publications are known.

Likewise, the yield monitor system may include a yield sensor for the harvester device that sends yield measurement data to the cab computer 115 or other equipment within the system 130. The yield monitor system may utilize one or more remote sensors 112 to obtain grain moisture measurements in a combine or other harvester and transmit these measurements to a user via the cab computer 115 or other device within the system 130.

In one embodiment, examples of sensors 112 that may be used with any moving vehicle or device of the type described elsewhere herein include kinematic sensors and positioning sensors. The kinematic sensor may include any speed sensor, such as a radar or wheel speed sensor, an accelerometer, or a gyroscope. The location sensor may include a GPS receiver or transceiver, or a WiFi-based location or mapping app programmed to determine location based on nearby WiFi hotspots, or the like.

In one embodiment, examples of sensors 112 that may be used with a tractor or other mobile vehicle include an engine speed sensor, a fuel consumption sensor, an area counter or distance counter that interacts with GPS or radar signals, a PTO (Power take off) speed sensor, a tractor hydraulic sensor configured to detect hydraulic parameters (such as pressure or flow) and/or hydraulic pump speed, a wheel speed sensor, or a wheel slip sensor. In one embodiment, examples of controllers 114 that may be used with a tractor include: a hydraulic directional controller, a pressure controller, and/or a flow controller; a hydraulic pump speed controller; a speed controller or governor; a hook positioning controller; or a wheel alignment controller that provides automatic steering.

In one embodiment, examples of sensors 112 that may be used with a seed planting device such as a planter, drill or air planter include: a seed sensor, which may be an optical, electromagnetic or impact sensor; a lower pressure sensor such as a load pin, a load sensor, a pressure sensor; soil property sensors such as reflectance sensors, moisture sensors, conductivity sensors, optical residue sensors, or temperature sensors; component operation standard sensors such as a planting depth sensor, a downcylinder pressure sensor, a seed tray speed sensor, a seed drive motor encoder, a seed conveyor system speed sensor, or a vacuum sensor; or a pesticide application sensor such as an optical or other electromagnetic sensor, or an impact sensor. In one embodiment, examples of controllers 114 that may be used with such seed planting equipment include: toolbar folding controllers, such as a controller for a valve associated with a hydraulic cylinder; a downforce controller, such as a controller associated with a pneumatic cylinder, an airbag, or a hydraulic cylinder, programmed to apply downforce to individual row units or the entire planter frame; a planting depth controller, such as a linear actuator; a metering controller, such as an electric seed-metering device drive motor, a hydraulic seed-metering device drive motor, or a swath control clutch; a hybrid selection controller, such as a seed meter drive motor, or is programmed to selectively allow or prevent the delivery of seeds or air seed mixtures to or from the seed meter or central bulk hopper; a metering controller, such as an electric seed meter drive motor or a hydraulic seed meter drive motor; a seed conveyor system controller, such as a controller for a belt seed transport conveyor motor; a marking controller, such as a controller for a pneumatic or hydraulic actuator; or pesticide application rate controllers such as metering drive controllers, orifice size or positioning controllers.

In one embodiment, examples of sensors 112 that may be used with a tilling apparatus include: a positioning sensor for a tool such as a handle or a disk; a tool positioning sensor for such a tool, the positioning sensor being configured to detect depth, rake angle or lateral spacing; a lower pressure sensor; or a traction force sensor. In one embodiment, examples of the controller 114 that may be used with the tilling apparatus include a hold down force controller or a tool positioning controller, such as a controller configured to control the depth of the tools, rake angle, or lateral spacing.

In one embodiment, examples of sensors 112 that may be used in association with an apparatus for applying fertilizer, insecticide, fungicide, etc. (such as activating a fertilizer system on a planter, a subsoil fertilizer applicator, or a fertilizer sprayer) include: fluidic system standard sensors, such as flow sensors or pressure sensors; a sensor indicating which of the spray head valve or the fluid line valve is open; a sensor associated with the tank, such as a liquid level sensor; segmented or system-wide supply line sensors, or line-specific supply line sensors; or a kinematic sensor such as an accelerometer positioned on the spray boom of the sprayer. In one embodiment, examples of controllers 114 that may be used with such devices include: a pump speed controller; a valve controller programmed to control pressure, flow, direction, PWM, etc.; or positioning actuators, such as for boom height, bed depth, or boom positioning.

In one embodiment, examples of sensors 112 that may be used with a harvester include: yield monitors such as impact plate strain gauges or positioning sensors, capacitive flow sensors, load sensors, weight sensors, or torque sensors associated with elevators or augers, or optical or other electromagnetic grain height sensors; cereal moisture sensors, such as capacitive sensors; grain loss sensors, including impact, optical or capacitive sensors; header operation standard sensors such as header height sensors, header type sensors, deck plate clearance sensors, feeder speed and reel speed sensors; the decoupler operates standard sensors such as recess plate clearance, rotor speed, shoe clearance or glume sieve clearance sensors; auger sensors for positioning, operation, or speed; or an engine speed sensor. In one embodiment, examples of controllers 114 that may be used with a harvester include: standard controllers for header operations such as header height, header type, deck gap, feeder speed, or reel speed; and a decoupler operating standard controller for features such as recess plate clearance, rotor speed, shoe clearance or glume sieve clearance; or an auger controller for positioning, operation, or speed.

In one embodiment, examples of sensors 112 that may be used with the cereal cart include weight sensors, or sensors for auger positioning, operation, or speed. In one embodiment, examples of controllers 114 that may be used with the cereal cart include controllers for auger positioning, operation, or speed.

In one embodiment, examples of the sensor 112 and controller 114 may be installed in an Unmanned Aerial Vehicle (UAV) device or "drone". Such sensors may include cameras having detectors effective for any range of the electromagnetic spectrum including visible light, infrared, ultraviolet, near Infrared (NIR), and the like; an accelerometer; a altimeter; a temperature sensor; a humidity sensor; pi Tuoguan sensor or other airspeed or wind speed sensor; a battery life sensor; or a radar transmitter and a reflected radar energy detection means; other electromagnetic radiation emitters and reflected electromagnetic radiation detection means. Such controllers may include a guidance or motor control, a control surface controller, a camera controller, or a controller programmed to turn on any of the aforementioned sensors, operate any of the aforementioned sensors, obtain data from any of the aforementioned sensors, manage and configure any of the aforementioned sensors. . Examples are disclosed in U.S. patent application Ser. No. 14/831,165, and the present disclosure assumes knowledge of other patent publications.

In one embodiment, the sensor 112 and controller 114 may be attached to a soil sampling and measuring device configured or programmed to sample soil and perform soil chemistry tests, soil moisture tests, and other soil related tests. For example, the devices disclosed in U.S. patent No.8,767,194 and U.S. patent No.8,712,148 may be used, and the present disclosure assumes knowledge of those patent disclosures.

In one embodiment, the sensor 112 and the controller 114 may include weather devices for monitoring weather conditions of the field. For example, the devices disclosed in U.S. provisional application number 62/154,207 filed on 29 th year 2015, U.S. provisional application number 62/175,160 filed on 12 th year 2015, U.S. provisional application number 62/198,060 filed on 7 th month 28 of 2015, and U.S. provisional application number 62/220,852 filed on 9 th month 18 of 2015 may be used, and the present disclosure assumes knowledge of those patent disclosures.

2.4. Process overview-agronomic model training

In one embodiment, agricultural intelligent computer system 130 is programmed or configured to create an agronomic model. In this context, an agronomic model is a data structure in the memory of agricultural intelligent computer system 130 that includes field data 106, such as identification data and harvest data for one or more fields. The agronomic model may also include calculated agronomic attributes describing conditions that may affect the growth of one or more crops in the field or the characteristics of one or more crops, or both. Additionally, the agronomic model may include recommendations based on agronomic factors such as crop recommendations, irrigation recommendations, planting recommendations, fertilizer recommendations, fungicide recommendations, pesticide recommendations, harvest recommendations, and other crop management recommendations. Agronomic factors may also be used to estimate results, such as agronomic yield, associated with one or more crops. The agronomic yield of a crop is an estimate of the number of crops produced, or in some examples, revenue or profit obtained from the crops produced.

In one embodiment, agricultural intelligent computer system 130 may use a preconfigured agricultural model to calculate agronomic attributes related to the location and crop information of one or more fields currently received. The preconfigured agronomic model is based on previously processed field data including, but not limited to, identification data, harvest data, fertilizer data, and weather data. The preconfigured agronomic model may have been cross-validated to ensure accuracy of the model. Cross-validation may include comparison with ground truth that compares predicted results with actual results on the field, such as comparing rainfall estimates with rain gauges or sensors that provide weather data at the same or nearby locations, or comparing estimates of nitrogen content with soil sample measurements.

FIG. 3 illustrates a programmed process by which an agricultural intelligence computer system generates one or more preconfigured agricultural models using field data provided by one or more data sources. Fig. 3 may serve as an algorithm or instruction for programming the functional elements of agricultural intelligent computer system 130 to perform the operations now described.

At block 305, the agricultural intelligent computer system 130 is configured or programmed to implement agricultural data preprocessing of field data received from one or more data sources. The field data received from one or more data sources may be preprocessed for the purpose of removing noise, distortion effects, and confounding factors within the agronomic data, including measurement outliers that may adversely affect the received field data values. Embodiments of agronomic data preprocessing may include, but are not limited to: certain measurement data points that remove data values typically associated with outlier data values, which are known to unnecessarily skew other data values, data smoothing, aggregation, or sampling techniques that are used to remove or reduce additive or multiplicative effects from noise, and other filtering or data derivation techniques that are used to provide a clear distinction between positive and negative data inputs.

At block 310, the agricultural intelligent computer system 130 is configured or programmed to perform data subset selection using the preprocessed field data to identify data sets useful for initial agricultural model generation. Agricultural intelligent computer system 130 may implement data subset selection techniques including, but not limited to, genetic algorithm methods, all subset model methods, sequential search methods, stepwise regression methods, particle swarm optimization methods, and ant colony optimization methods. For example, genetic algorithm selection techniques use adaptive heuristic search algorithms to determine and evaluate datasets within pre-processed agronomic data based on natural selection and evolutionary principles of genetics.

At block 315, agricultural intelligent computer system 130 is configured or programmed to implement a field dataset evaluation. In one embodiment, a particular field data set is evaluated by creating an agronomic model and using a particular quality threshold for the created agronomic model. One or more comparison techniques may be used to compare and/or verify the agronomic model, such as, but not limited to, leave-one-out cross-verified Root Mean Square Error (RMSECV), mean absolute error, and mean percent error. For example, RMSECV may cross-verify an agronomic model by comparing predicted agronomic attribute values created by the agronomic model with historical agronomic attribute values that are collected and analyzed. In one embodiment, the agronomic data set evaluation logic is used as a feedback loop, wherein agronomic data sets that do not meet the configured quality threshold are used during a future data subset selection step (block 310).

At block 320, agricultural intelligent computer system 130 is configured or programmed to implement agricultural model creation based on the cross-validated agricultural data set. In one embodiment, the agronomic model creation may implement a multivariate regression technique to create a preconfigured agronomic data model.

At block 325, the agricultural intelligent computer system 130 is configured or programmed to store the preconfigured agricultural data model for future field data evaluations.

2.5. Implementation example-hardware overview

According to one embodiment, the techniques described herein are implemented by one or more special purpose computing devices. The special purpose computing device may be hardwired to perform the techniques, or may include a digital electronic device, such as one or more Application Specific Integrated Circuits (ASICs) or Field Programmable Gate Arrays (FPGAs) permanently programmed to perform the techniques, or may include one or more general purpose hardware processors programmed to perform the techniques in accordance with program instructions in firmware, memory, other storage, or a combination. Such special purpose computing devices may also incorporate custom hard-wired logic, ASICs, or FPGAs in combination with custom programming to accomplish these techniques. The special purpose computing device may be a desktop computer system, portable computer system, handheld device, networking device, or any other device that incorporates hardwired and/or program logic to implement these techniques.

For example, FIG. 4 is a block diagram that illustrates a computer system 400 upon which an embodiment of the invention may be implemented. Computer system 400 includes a bus 402 or other communication mechanism for communicating information, and a hardware processor 404 coupled with bus 402 for processing information. The hardware processor 404 may be, for example, a general purpose microprocessor.

Computer system 400 also includes a main memory 406, such as a Random Access Memory (RAM) or other dynamic storage device, coupled to bus 402 for storing information and instructions to be executed by processor 404. Main memory 406 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by processor 404. When such instructions are stored in a non-transitory storage medium accessible to the processor 404, the computer system 400 is rendered into a special purpose machine that is customized to perform the operations specified in the instructions.

Computer system 400 also includes a Read Only Memory (ROM) 408 or other static storage device coupled to bus 402 for storing static information and instructions for processor 404. A storage device 410, such as a magnetic disk, optical disk, solid state drive, is provided and coupled to bus 402 for storing information and instructions.

Computer system 400 may be coupled via bus 402 to a display 412, such as a Cathode Ray Tube (CRT), for displaying information to a computer user. An input device 414, including alphanumeric and other keys, is coupled to bus 402 for communicating information and command selections to processor 404. Another type of user input device is cursor control 416, such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections to processor 404 and for controlling cursor movement on display 412. The input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), which allows the device to specify positioning in a plane.

Computer system 400 may implement the techniques described herein using custom hardwired logic, one or more ASICs or FPGAs, firmware, and/or program logic, in conjunction with a computer system, to make computer system 400 a special purpose machine or to program computer system 400 into a special purpose machine. According to one embodiment, the techniques herein are performed by computer system 400 in response to processor 404 executing one or more sequences of one or more instructions contained in main memory 406. Such instructions may be read into main memory 406 from another storage medium, such as storage device 410. Execution of the sequences of instructions contained in main memory 406 causes processor 404 to perform the process steps described herein. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions.

The term "storage medium" as used herein refers to any non-transitory medium that stores data and/or instructions that cause a machine to operate in a specific manner. Such storage media may include non-volatile media and/or volatile media. Non-volatile media includes, for example, optical disks, magnetic disks, or solid state drives, such as storage device 410. Volatile media includes dynamic memory, such as main memory 406. Common forms of storage media include, for example, a floppy disk, a flexible disk, hard disk, solid state drive, magnetic tape, or any other magnetic data storage medium, a CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, NVRAM, any other memory chip or cartridge.

Storage media are different from, but may be used in conjunction with, transmission media. Transmission media participate in the transfer of information between storage media. For example, transmission media includes coaxial cables, copper wire and fiber optics, including the wires that comprise bus 402. Transmission media can also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

Various forms of media may be involved in carrying one or more sequences of one or more instructions to processor 404 for execution. For example, the instructions may initially be carried on a magnetic disk or solid state drive of a remote computer. The remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to computer system 400 can receive the data on the telephone line and use an infra-red transmitter to convert the data to an infra-red signal. An infra-red detector can receive the data carried in the infra-red signal and appropriate circuitry can place the data on bus 402. Bus 402 carries the data to main memory 406, from which main memory 406 processor 404 retrieves and executes the instructions. The instructions received by main memory 406 may optionally be stored on storage device 410 either before or after execution by processor 404.

Computer system 400 also includes a communication interface 418 coupled to bus 402. Communication interface 418 provides a two-way data communication coupling to a network link 420 that is connected to a local network 422. For example, communication interface 418 may be an Integrated Services Digital Network (ISDN) card, a cable modem, a satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, communication interface 418 may be a Local Area Network (LAN) card to provide a data communication connection to a compatible LAN. Wireless links may also be implemented. In any such implementation, communication interface 418 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.

Network link 420 typically provides data communication through one or more networks to other data devices. For example, network link 420 may provide a connection through local network 422 to a host computer 424 or to data equipment operated by an Internet Service Provider (ISP) 426. ISP426 in turn provides data communication services through the world wide packet data communication network now commonly referred to as the "Internet" 428. Local network 422 and internet 428 both use electrical, electromagnetic or optical signals that carry digital data streams. The signals through the various networks and the signals on network link 420 and through communication interface 418, which carry the digital data to and from computer system 400, are exemplary forms of transmission media.

Computer system 400 can send messages and receive data, including program code, through the network(s), network link 420 and communication interface 418. In the internet example, a server 430 might transmit a requested code for an application program through internet 428, ISP426, local network 422 and communication interface 418.

The received code may be executed by processor 404 as it is received, and/or stored in storage device 410, or other non-volatile storage for later execution.

3. Generating inferred controls using spatial modeling

FIG. 7 depicts a method for inferring control data for an agronomic test using a spatial statistical model. Although fig. 7 uses yield data as an example, the methods described herein may be utilized to infer control data for other properties of interest, such as grain quality, protein content, and other factors assessed and/or measured by experimentation. As used herein, a test refers to performing one or more different agricultural activities in a portion of an agricultural field in order to identify benefits or hazards of performing the one or more different agricultural activities. For example, sub-field areas may be selected in an agricultural field to achieve a fungicide test. Within a sub-field region, the crop may receive the application of the fungicide while the remainder of the field and/or a different sub-field region on the field does not receive the application of the fungicide. Alternatively, the remainder of the field may receive the application of the fungicide, while crops within the sub-field area do not. The sub-field region of the field in which one or more different agricultural activities are performed is referred to herein as a test location. In some embodiments, sub-field regions that do not include different agricultural activities may also be assigned and referred to as test locations.

Experiments may be performed to test the efficacy of new products, different management practices, different crops, or any combination thereof. For example, if the field does not normally receive a fungicide, a test may be designed in which crops within a selected portion of the field receive the fungicide one or more times during crop development. As another example, if the field is normally cultivated, a test may be designed in which selected portions of the field are not cultivated. Thus, rather than being limited to testing the efficacy of a particular product, testing can be accomplished to determine whether to follow regulatory practice recommendations. Additionally or alternatively, trials may be designed to compare two different types of products, planting rates, equipment, and/or other management practices.

The trial may be constrained by one or more rules. The test may require that one or more test sites be of a particular size and/or be disposed at a particular location. For example, a test may require that one or more test locations be placed in a region of a field that is comparable to the rest of the field. As used herein, a test location refers to a region of an agricultural field that receives one or more treatments that are different from surrounding regions. Thus, a test site may refer to any shape of land on an agricultural field. Additionally or alternatively, the test may require that one or more test locations be arranged in a region of the field that is different from the rest of the field conditions and/or a region of the field that spans fields of different types of conditions. The trial may require one or more different management practices to be performed at one or more test sites. For example, as part of a test to plant different types of hybrid seeds, the test may require a specific sowing rate.

In one embodiment, the methods described herein are used to cause implementation of an experiment. For example, the methods described herein may be used to identify locations in an agricultural field for performing trials. The methods described herein may also be used to generate agricultural scripts including computer readable instructions for: the computer readable instructions, when executed, cause the agricultural implement to perform an action on the field according to the test. In one embodiment, the methods described herein are used to determine the efficacy of an assay and to cause performance of a responsive action. For example, if the method determines that the test process is more effective than the non-test process, the method may include generating a prescription map that includes the test process over a larger portion of the agronomic field. The method may further include generating an agricultural script comprising computer-readable instructions to: the computer readable instructions, when executed, cause the agricultural implement to perform an action on the field based on the results of the test.

3.1. Received data

At step 702, first yield data for a first portion of an agronomic field is received, the first portion of the agronomic field having received a first treatment. For example, the agricultural intelligent computer system may receive yield data from a field manager computing device, an agricultural implement, an external computing device, and/or an imaging device. The first yield data may include average agronomic yield values for a plurality of locations on an agricultural field. For example, a harvester can measure agronomic yield while harvesting crops for a 10 x 10 square meter location, thereby generating a pixel map of agronomic yield values. Additionally or alternatively, the yield data may include index values, such as normalized difference vegetation index values (NDVI), generated from images of the agronomic field, such as images captured using the drone and/or satellite.

As used herein, the first process refers to one or more management practices performed in a non-trial location. For example, the first process may include any of the following: specific seed populations, crossing types, seed types, pesticide application, nutrient application, or other management practices. The server computer may receive data indicating a location on the agronomic field where the first treatment has been received.

At step 704, second yield data is received for a second portion of the agronomic field that has received a second treatment different from the first treatment. For example, the agricultural intelligent computer system may receive yield data from a field manager computing device, an agricultural implement, an external computing device, and/or an imaging device.

The second process may be a test process different from the first process. For example, if the first treatment is the application of a fungicide, the second treatment may be the application of a different fungicide. In one embodiment, the second portion of the agronomic field is treated the same as the first portion of the agronomic field except for the differences in the first treatment and the second treatment. For example, the same seed hybrid may be planted in the same population at both locations, but a second portion of the agronomic field may receive a different fertilizer application than the first portion of the agronomic field.

In one embodiment, the second portion of the agronomic field includes one or more test strips. As used herein, a test refers to performing one or more different agricultural activities in a portion of an agricultural field in order to identify benefits or hazards of performing the one or more different agricultural activities. As used herein, a test strip refers to a location on an agronomic field that may be treated in one or more complete passes of an agronomic vehicle. In one embodiment, the first portion of the agricultural field at least partially surrounds the second portion of the agricultural field. For example, the first portion of the agricultural field may be a strip on one side of the second portion, a strip on both sides of the second portion, a field remainder other than the test location, and/or any portion of the agricultural field at least partially adjacent to the second portion.

3.2. Statistical model

At step 706, yield values for a second portion of the agronomic field are calculated using the spatial statistical model and the first yield data. The yield value indicates an agronomic yield for the second portion of the agronomic field if the second portion of the agronomic field has received the first treatment but not the second treatment. For example, the yield value may include a yield value for each of a plurality of locations in the second portion of the agricultural field and/or an average yield for the second portion of the agricultural field.

In one example embodiment, the agronomic field is divided into a plurality of equally sized grid points, such as 10 x 10 square meters of locations. The yield value for the first portion of the agronomic field is used to calculate a value for the second portion of the agronomic field using a spatial statistical model:

y(s _i )＝μ+w(s _i )+∈ _i

wherein y(s) _i ) Is for position s _i Yield at the ith grid point, μ is the overall average yield for the agronomic field except for the second portion of the agronomic field, w (s _i ) Is a spatially dependent process and e _i Is a small scale error process that can be fitted based on field variances between calculations using spatial statistical models and actual production at these locations.

In one embodiment, the spatially dependent process w (s _i ) Is a zero-mean spatially correlated gaussian process, such as with variance τ ² And a spatial correlation function k _p Is a gaussian random field equation of (c). Thus, the distribution of grid point vectors in the second portion for the agronomic field may be calculated as:

the distribution may be calculated as a gaussian process model with a constant mean function. Matrix K _p Comprising a variance-covariance matrix, wherein the ij-th element consists of k _p (s _i ，s _j ) Given. The system may use the yield values at locations in the first portion of the agronomic field to parameterize the gaussian process. Based on the yield values in the locations in the first portion of the agronomic field, the variance and standard deviation parameters τ and σ may be parameterized using any parameterization method, such as a maximum likelihood estimation method.

By using a statistical spatial process, the methods described herein can infer yield values for each of a plurality of test locations (such as test strips) based on different application types. Thus, the spatial procedure is used to infer what the product value would be for a test location if that location received a different treatment. An example implementation of the fitting of the above model includes using the GSTAT package available on gitub.

While the methods described herein are capable of using only the yield data of the current year to generate yield values for test locations based on non-test processing, the spatial model may be enhanced if yield data from a previous year is available. By utilizing previous year yield data in a gaussian process model, the method is able to capture spatial variability within test sites. For example, a yield map from the first year may include yield data in which the entire field receives the same process. Thus, based on the spatial variability of yield in yield data from the first year, where test locations receive the same treatment as the rest of the field, the spatial variability in test locations for the second year, where test locations receive different treatments, can be modeled.

In one embodiment, the agricultural intelligent computer system models the inferred yields in the second portion of the agronomic field as a function of one or more covariates. The one or more covariates can include additional values related to agronomic yield at different locations on an agronomic field. Examples of covariates may include: percentage of organics, pH, cation exchange capacity, elevation, soil type, nutrient level, NDVI value when measured yield values are utilized, and/or any other measurable attribute that may vary in an agronomic field. Data for covariate values may be received from an external server, such as a soil survey geographic database (SSURGO), through input from a field manager computing device, and/or directly or indirectly from agricultural implements operating on an agricultural field configured to measure one or more of the covariates described above.

As an example, the yield value for the second portion of the agronomic field may be calculated using the following function:

y(s _i )＝μ+x _i β+w(s _i )+∈ _i

wherein x is _i Is a vector of covariates for the ith grid point and β is an associated parameter vector estimated or fitted using the current production data and/or the previous year's production data.

In one embodiment, the agricultural intelligent computer system jointly models yield data in the second portion of the agricultural field and in the first portion of the agricultural field using data from the first portion of the agricultural field and the second portion of the agricultural field for fitting a model. An example equation for modeling agronomic yield in both the first and second portions of the agronomic field is as follows:

y(s _i )＝μ+δu _i +x _i β+w(s _i )+∈ _i

where delta is the effect of applying a second treatment to a second portion of the agronomic field, but not the first treatment, u _i Is a process indicator equal to 0 for each location in which the first process is applied and equal to 1 for each location in which the second process is applied. Although in the previous equation, y (s _i ) Is used to calculate the inferred yield in the second portion of the agronomic field if the second portion received the first treatment, but in the equation above, y (s _i ) Including the measured yields in each location, and fitted to a gaussian process to estimate the average impact delta of applying the second treatment to the second portion of the agronomic field.

In one embodiment, a separate spatial variability model is used to calculate the estimated impact of applying the second treatment to the second portion of the agronomic field instead of the first treatment. For example, the agricultural intelligence computer system may fit a spatial model to:

Wherein isA spatial model for the location in which the first process is applied, and +.>Is a spatial model for the location where the second process is applied. The two parts of the agronomic field do not share parameters characterizing the spatial variability, but are such as by intrinsicThe co-localization model, two spatial models are assumed to be correlated.

Although the method is described above with respect to two processes, the method described herein may be utilized with multiple processes in multiple locations. For example, if an agronomic field includes two strip trials and one primary treatment, the yield in the primary treatment location may be used to generate a spatial model for calculating inferred yields using the primary treatment in other locations. As another example, two effects of applying either of two processes may be calculated as:

y(s _i )＝μ+δ ₁ u _1，i +δ ₂ u _2，i +x _i β+w(s _i )+∈ _i

wherein delta ₁ Is the effect of applying a second treatment, delta, to an agronomic field ₂ Is the effect of applying a third treatment to an agronomic field, u _1，i 1 when the second process is applied, 0 at all other times, and u _2，i The third process is applied at 1 and at 0 at all other times.

Although the above example describes equally sized grid locations of 10 x 10 square meters, in some cases, data may be received at different resolutions based on field. When data is received at finer resolution, it may render the gaussian model computationally infeasible to compute, as complexity grows by a third power of the number of data points. In addition, some spatial correlation structures for agronomic data may be more complex and less stable. Thus, techniques can be used to better model complex spatial structures while reducing computational complexity.

In one embodiment, a fixed rank kriging model is used to reduce the computational scalability of a larger sized data set. In the fixed rank kriging technique, the vector S is defined as a sequence of basis functions. Correlation matrix K _p Can thus be defined as:

K _p ＝SMS′

the correlation matrix may then be incorporated into the above model. The M matrix may be a ratio K _p Smaller rank matrix. The unknown, symmetric, positive definite matrix M can be estimated from the agronomic data using the binning method of the moment estimation process.

In one embodiment, a discrete process convolution model is used to reduce the computational cost of using large datasets while also capturing more complex spatial correlation structures. The discrete process convolution model may comprise a multi-resolution model whereby a plurality of progressively coarsened grid sets for a particular data set are defined. For example, if yield data for a particular field is received with a higher spatial resolution, such as 5 x 5 square meters of locations, a first grid with 5 x 5 square meters of locations may be generated, a coarser second grid with 10 x 10 square meters of locations may be generated, and so on. The model may be calculated using each of the r grid points, such as by the following equation:

Wherein the method comprises the steps ofIs at inclusion position s _j Is a grid of all positions in the grid. The parameter +.>And epsilon _i 。

In one embodiment, the correlation functionMay be selected to have a tight branch, such as a spherical correlation function. Then when the model is expressed in matrix form, the correlation matrix K will be sparse and have a structure that can be utilized by dedicated software (such as the spark. Linking module of the PYTHON SCIPY package) to improve the computational efficiency.

3.3. Determining test impact

At step 708, a second process is selected based at least in part on the calculated yield value and the second yield data. For example, the agricultural intelligent computer system may determine the standard deviation of any of the above yield models. The system may calculate an average of the inferred yields for the second portion of the agronomic field. The system may use the mean and standard deviation of the inferred yields to calculate one or more thresholds. For example, the system may calculate the upper threshold as the average inferred yield plus 1.6 times the standard deviation of yield, thereby generating the upper 90% threshold. The system may also calculate the lower threshold as the average inferred yield minus 1.6 times the standard deviation of yield, thereby generating the lower 90% threshold.

The agricultural intelligence computer system may use the calculated threshold to determine whether the second treatment has a statistically significant effect on the agronomic field. For example, the agricultural intelligence computer system may calculate an average yield for a second portion of the agronomic field based on the yield data received for the second portion of the agronomic field. If the calculated average yield for the second portion of the agronomic field is greater than the upper threshold, the system may determine that the second treatment has a beneficial effect and select the second treatment. If the calculated average yield for the second portion of the agronomic field is below the lower threshold, the system may determine that the second treatment has a detrimental effect and select the first treatment.

In one embodiment, the agricultural intelligent computer system utilizes the previous year's yield data to determine a standard deviation for the second portion of the agronomic field. For example, the agricultural intelligent computer system may receive the previous year's yield data, wherein both the first portion of the agricultural field and the second portion of the agricultural field received the same treatment. The system may calculate a yield value for a second portion of the agronomic field based on the first portion of the agronomic field using the spatial model described herein. The system may then calculate a difference value for each location in the second portion of the agronomic field, the difference value comprising a difference between the calculated yield and the actual yield using the spatial model. The system may then fit the variance values to a distribution, such as a normal distribution, and calculate the standard deviation of the fit distribution. If data for multiple previous years is available, the system may perform the method for each previous year and use the average standard deviation across the multiple years.

3.4. Practical application of statistical model

The systems and methods described herein utilize a spatial statistical model to determine whether the results of an agronomic test are statistically significant, allowing the system to generate a prescription map based on the results of the test, generate scripts based on the results of the test, display data indicative of the benefit or harm of the test, and/or display a map identifying the test results in a plurality of locations and data indicative of the significance of the test results.

As an example of a practical application, at step 710, in response to selecting the second process, a prescription map is generated, the prescription map including the second process. For example, if the agricultural intelligent computer system determines that the second process is beneficial using the methods described herein, the system may select that the second process be applied to a larger portion of the field. Thus, the system may generate a prescription map comprising a spatial map of the agronomic field with data indicative of the application of those treatments to different locations of the field. The prescription map may include a second treatment applied to a field portion that is larger than a second portion of the agricultural field. For example, if the process is initially applied to a single test strip, the system may generate a prescription map that includes multiple test strips, an entirety of the management zone, an entire section of the agronomic field, an entirety of the agronomic field excluding being used for different tests, and/or an entire agronomic field.

By automatically generating the prescription map in response to selection of the second process, the system can utilize the spatial statistical model as part of the practice of generating the prescription map. The system is also capable of implementing a change in management practice in response to not only an increase in agronomic yield from one location to another, but also an increase in agronomic yield in a single location as compared to an estimated yield for that location and/or determining that the increase in agronomic yield is statistically significant.

In one embodiment, if the agricultural intelligent computer system determines that the increase or decrease in yield is not statistically significant and/or if the system determines that the decrease in yield is statistically significant, the system is programmed or configured to perform a responsive action. For example, if the agricultural intelligent computer system determines that the agricultural yield in the second portion of the agricultural field is at least 1.6 standard deviations less than the inferred agricultural yield for the second portion of the agricultural field, the system may generate a future prescription map that completely excludes the second process. Additionally or alternatively, if the system determines that the results are statistically insignificant, the system may generate a new prescription map that includes a second treatment applied to a second portion of the agronomic field and/or one or more different portions of the agronomic field.

As an additional example of a practical embodiment, at step 712, one or more scripts are generated. The script includes computer readable instructions that, when executed by the application controller, cause the application controller to control an operating parameter of an implement on the agronomic field (such as agricultural device 111) to apply the second process. The script may be configured to match the generated prescription map such that the script, when executed, causes the one or more agricultural implements to execute the prescription in the prescription map. The agricultural intelligent computer system may send scripts to the field manager computing device and/or the application controller over a network.

For example, if the second process includes a different seed population than the first process, the system may generate instructions that, when executed, cause the planter to release seeds onto the field at the population rate of the second process in a location on the agronomic field that matches the generated prescription map. Other examples of scripts include nutrient application scripts, pesticide scripts, and/or other planting scripts that alter seed types or seed crosses. Thus, the methods described herein may be used to operate agricultural machinery based on determinations performed by experiments generated from a spatial statistical model.

4. Using spatial modeling to identify trial positions

FIG. 8 depicts a method for selecting a location for performing an experiment using a spatial statistical model. At step 802, yield data for an agronomic field is received, the agronomic field having received a first process. For example, the agricultural intelligent computer system may receive yield data from a field manager computing device, an agricultural implement, an external computing device, and/or an imaging device. The yield data may include average agronomic yield values for a plurality of locations on an agricultural field. For example, a harvester can measure agronomic yield while harvesting crops for a 10 x 10 square meter location, thereby generating a pixel map of agronomic yield values. Additionally or alternatively, the yield data may include index values, such as normalized difference vegetation index values (NDVI), generated from images of the agronomic field, such as images captured using the drone and/or satellite.

As used herein, the first process refers to one or more management practices performed on an agronomic field. For example, the first process may include any of the following: specific seed populations, crossing types, seed types, pesticide application, nutrient application, or other management practices. The server computer may receive data indicating a location on the agronomic field where the first treatment has been received.

4.1. Statistical model

At step 804, the spatial statistical model is used to calculate an average statistical deviation value for each of a plurality of particular portions of the agronomic field. For example, the system may identify a plurality of locations where an agronomic field test can be performed. Identifying the plurality of locations may include identifying locations within a portion of the agronomic field that receive the same treatment matching one or more criteria. For example, the agricultural intelligent computer system may identify locations on the agricultural field that have at least a particular length and/or width, have a certain amount of space around them, and/or meet any other criteria.

For each identified location, the system may calculate an average deviation. First, for a particular portion of an agronomic field, a yield value is calculated using a spatial statistical model and yield data for individual portions of the field. For example, the system may utilize the statistical model described in section 3.2 to calculate a yield value in one location within a portion of an agronomic field receiving the same treatment based on the remaining portion. Thus, if the particular portion is a stripe in the middle of an agronomic field, the system may use all yield data in the agronomic field except the stripe to generate a statistical spatial model and use the statistical spatial model to calculate yield values in the stripe.

Then, using the yield value and the portion of the yield data corresponding to the particular portion of the agronomic field, an average statistical deviation value for the particular portion of the agronomic field is calculated. For example, for each location in a particular portion of the field, the system may calculate a difference between the yield value from the yield data and the yield value calculated from the statistical spatial model. The system may calculate an average difference in values in a particular portion of the agronomic field. Additionally or alternatively, the system may calculate an average of the absolute values of the differences, indicating an average overall variability from the statistical model. Additionally or alternatively, the system may use the variance values to calculate standard deviations for particular portions of the agronomic field under the assumption that the statistical model follows a normal distribution. The system may then perform the same process on one or more other portions of the agronomic field.

4.2. Selecting a portion of an agronomic field

At step 806, one or more of the plurality of particular portions of the agricultural field is selected as a test portion of the agricultural field based on the average statistical deviation value for each of the plurality of particular portions of the agricultural field. For example, the agricultural intelligence computer system may select one or more locations having the lowest average statistical deviation. By selecting the location with the lowest average statistical deviation, the system can increase the statistical significance of the benefit or loss in the test location on the agronomic field, thereby reducing the amount of agronomic field that needs to be treated differently to produce a statistically significant result and/or allowing a statistically significant result to be produced at a lesser level of benefit or harm.

In one embodiment, the agricultural intelligence computer system determines whether to select a location or locations based on the calculated bias values. For example, the agricultural intelligent computer system may determine the expected benefit of the second process, such as by modeling the benefit and/or receiving data defining the expected benefit. The agricultural intelligence computer system may determine that the expected benefit would not be a greater than 1.6 standard deviation benefit if shown in a single portion of the agricultural field, but the expected benefit would be a greater than 1.6 standard deviation 1.6 benefit if shown in two portions of the agricultural field. In response, the system may select two portions of the agronomic field for the second treatment in order to ensure that the expected benefit is statistically significant.

The methods described herein may be performed using one or more models described in section 3.2. For example, if the field includes three possible test locations, the system may calculate an average deviation for each of the three possible test locations using a statistical model without covariates, and calculate an average deviation for each of the three possible test locations using a statistical model with covariates. The system may then select the combination of location and model type with the lowest average deviation.

4.3. Practical application of location identification

The systems and methods described herein utilize a spatial statistical model to identify locations where the results of an agronomic trial are more likely to be statistically significant, allowing the system to generate prescription maps to implement the trial based on previous year production data (such as a production map), generate scripts to implement the trial, display data identifying the best locations for implementing the trial, and/or display a map identifying the best locations for implementing the trial.

As an example of a practical application, at step 808, in response to selecting a trial portion of the agronomic field, a prescription map is generated, the prescription map including a second process in the trial portion that is different from the first process. For example, if the agricultural intelligent computer system identifies a particular stripe having the lowest statistical deviation value, the system may select a location for performing an experiment using a second process that is different from the first process. The system may generate a prescription map including an agronomic field space map with data indicating that the second treatment is to be applied to a particular portion of the field and that the first treatment is to be applied to one or more other portions of the field (such as the remainder of the agronomic field).

The system may select a first process for a region of the map that was originally used to generate bias values for a selected portion of the agronomic field. For example, if the system creates each statistical model using only strips of limited width on either side of a particular portion of the agronomic field, the system may generate the prescription map such that at least the selected portion of the agronomic field has the second treatment and strips of limited width on either side of the selected portion receive the first treatment.

By automatically generating a prescription map in response to selection of one or more particular portions of an agronomic field, the system can utilize a spatial model as part of the practical process of generating a prescription map for implementing the trial. The system is additionally capable of reducing the amount of agronomic field used for testing, thereby reducing the adverse impact of the test on the agronomic field while improving the efficacy of the test.

As an additional example of a practical embodiment, at step 812, one or more scripts are generated. The script includes computer readable instructions that, when executed by the application controller, cause the application controller to control an operating parameter of an agricultural implement on the agricultural field to apply the second treatment to the test portion of the agricultural field. The script may be configured to match the generated prescription map such that the script, when executed, causes the one or more agricultural implements to execute the prescription in the prescription map. The agricultural intelligent computer system may send scripts to the field manager computing device and/or the application controller over a network.

As an example, if the second process includes a different seed population than the first process, the system may generate instructions that, when executed, cause the seed planter to release seeds onto the field at a population rate of the second process in a selected location on the agronomic field that matches the generated prescription map. Other examples of scripts include nutrient application scripts, pesticide scripts, and/or other planting scripts that alter seed types or seed crosses. Thus, the methods described herein may be used to operate agricultural machinery based on determinations performed by experiments generated from a spatial statistical model.

5. Benefits of certain embodiments

When considered in view of the description herein and its overall features, the present disclosure is directed to improvements in the operational control of field instruments and equipment in agriculture, which improvements are based on improvements in the computer-implemented calculations of prescription maps for the yield values, treatment, and designation of where in the field what fertilizer or other nutrient is applied to the agricultural field. This disclosure is not intended to cover or claim an abstract concept of determining yield, processing, or prescription, but rather to cover or claim a practical application of using a computer to control agricultural machinery as set forth hereinabove.

The systems and methods described herein provide practical applications that utilize field data to maximize efficient management of an agronomic field using an agricultural machine. By modeling the control of the test in the same area as the test, the system can maximize the effective and efficient use of agricultural land by minimizing the area required to determine whether the test has a statistically significant positive or negative impact. Thus, by leaving less area for performing trials, agricultural fields can benefit from the modeling techniques provided.

Additionally, the systems and methods described herein utilize field information as part of a process of physically implementing tests on an agricultural field using agricultural implements and/or utilizing test results that would otherwise not be available as part of a physical process of implementing management practices on an agricultural field using agricultural implements. The agricultural intelligence computer system can use the methods described herein to generate a prescription map defining management instructions for testing locations and/or defining management instructions for an agronomic field based on test results. Additionally or alternatively, the agricultural intelligence computer system can use the methods described herein to generate one or more scripts that, when executed, cause the agricultural implement to perform particular actions on the agricultural field and to perform different actions at the test location, and/or to alter actions performed on the field in response to test results.

6. Expansion and alternatives

In the foregoing specification, embodiments have been described with reference to numerous specific details that may vary from implementation to implementation. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense. The sole and exclusive indicator of the scope of the disclosure, and what applicant intends to be the scope of the disclosure, is the literal and equivalent scope of the set of claims that issue from this application, in the specific form in which such claims issue, including any subsequent correction.

Claims (20)

1. A system, comprising:

one or more processors;

a memory storing instructions that, when executed by the one or more processors, cause performance of:

receiving first yield data for a first portion of an agronomic field, the first portion of the agronomic field having received a first treatment;

receiving second yield data for a second portion of the agronomic field, the second portion of the agronomic field having received a second treatment different from the first treatment;

calculating, using a spatial statistical model and the first yield data, a yield value for the second portion of the agronomic field, the yield value indicating an agronomic yield for the second portion of the agronomic field if the second portion of the agronomic field has received the first treatment but not the second treatment;

Selecting the second process based on the calculated yield value and the second yield data;

generating a prescription map based on the spatial statistical model, the prescription map including the second process;

one or more scripts are generated that, when executed by an application controller, cause the application controller to control operating parameters of an agricultural implement to apply the second process.

2. The system of claim 1, wherein the first process and the second process comprise one or more of: specific seed populations, hybridization types, pesticide application, or nutrient application.

3. The system of claim 1, wherein the spatial statistical model is configured to calculate yield values as a function of a spatially dependent gaussian process.

4. The system of claim 1, wherein the spatial statistical model is configured to model yield as a function of one or more of: percentage of organics, pH, cation exchange capacity, elevation, soil type, or nutrient level.

5. The system of claim 1, wherein selecting the second process comprises:

calculating an upper threshold based on the calculated yield value;

Determining that a yield of the second yield data is greater than the calculated yield value, and in response, selecting the second process.

6. A system, comprising:

one or more processors;

a memory storing instructions that, when executed by the one or more processors, cause performance of:

receiving yield data for an agronomic field, the agronomic field having received a first treatment;

for each particular portion of the plurality of particular portions of the agronomic field, performing:

calculating a yield value for the particular portion of the agronomic field using a spatial statistical model and yield data for individual portions of the agronomic field;

calculating an average statistical deviation value for the particular portion of the agronomic field using the yield value and a portion of the yield data corresponding to the particular portion of the agronomic field;

selecting one or more of the plurality of particular portions of the agricultural field as a test portion of the agricultural field based on the average statistical deviation values for each of the plurality of particular portions of the agricultural field;

Generating a prescription map based on the spatial statistical model, wherein the prescription map includes a second process in the trial portion that is different from the first process;

one or more scripts are generated that, when executed by an application controller, cause the application controller to control operating parameters of an agricultural implement to apply the second treatment to the test portion of the agronomic field.

7. The system of claim 6, wherein the first process and the second process comprise one or more of: specific seed populations, hybridization types, pesticide application, or nutrient application.

8. The system of claim 6, wherein the spatial statistical model is configured to calculate yield values as a function of a spatially dependent gaussian process.

9. The system of claim 6, wherein the spatial statistical model is configured to model yield as a function of one or more of: percentage of organics, pH, cation exchange capacity, elevation, soil type, or nutrient level.

10. The system of claim 6, wherein selecting one or more of the plurality of particular portions of the agronomic field as a test portion of the agronomic field comprises: one or more portions of the plurality of particular portions of the agronomic field having the lowest average statistical deviation are selected.

11. A computer-implemented method, comprising:

receiving first yield data for a first portion of an agronomic field, the first portion of the agronomic field having received a first treatment;

receiving second yield data for a second portion of the agronomic field, the second portion of the agronomic field having received a second treatment different from the first treatment;

calculating, using a spatial statistical model and the first yield data, a yield value for the second portion of the agronomic field, the yield value indicating an agronomic yield for the second portion of the agronomic field if the second portion of the agronomic field has received the first treatment but not the second treatment;

selecting the second process based on the calculated yield value and the second yield data;

generating a prescription map based on the spatial statistical model, the prescription map including the second process;

one or more scripts are generated that, when executed by an application controller, cause the application controller to control operating parameters of an agricultural implement to apply the second process.

12. The computer-implemented method of claim 11, wherein the first process and the second process comprise one or more of: specific seed populations, hybridization types, pesticide application, or nutrient application.

13. The computer-implemented method of claim 11, wherein the spatial statistical model is configured to calculate yield values as a function of a spatially dependent gaussian process.

14. The computer-implemented method of claim 11, wherein the spatial statistical model is configured to model yield as a function of one or more of: percentage of organics, pH, cation exchange capacity, elevation, soil type, or nutrient level.

15. The computer-implemented method of claim 11, wherein selecting the second process comprises:

calculating an upper threshold based on the calculated yield value;

determining that a yield of the second yield data is greater than the calculated yield value, and in response, selecting the second process.

16. A computer-implemented method, comprising:

receiving yield data for an agronomic field, the agronomic field having received a first treatment;

For each particular portion of the plurality of particular portions of the agronomic field, performing:

calculating a yield value for the particular portion of the agronomic field using a spatial statistical model and yield data for individual portions of the agronomic field;

calculating an average statistical deviation value for the particular portion of the agronomic field using the yield value and a portion of the yield data corresponding to the particular portion of the agronomic field;

selecting one or more of the plurality of particular portions of the agricultural field as a test portion of the agricultural field based on the average statistical deviation values for each of the plurality of particular portions of the agricultural field;

generating a prescription map based on the spatial statistical model, wherein the prescription map includes a second process in the trial portion that is different from the first process;

one or more scripts are generated that, when executed by an application controller, cause the application controller to control operating parameters of an agricultural implement to apply the second treatment to the test portion of the agronomic field.

17. The computer-implemented method of claim 16, wherein the first process and the second process comprise one or more of: specific seed populations, hybridization types, pesticide application, or nutrient application.

18. The computer-implemented method of claim 16, wherein the spatial statistical model is configured to calculate yield values as a function of a spatially dependent gaussian process.

19. The computer-implemented method of claim 16, wherein the spatial statistical model is configured to model yield as a function of one or more of: percentage of organics, pH, cation exchange capacity, elevation, soil type, or nutrient level.

20. The computer-implemented method of claim 16, wherein selecting one or more of the plurality of particular portions of the agronomic field as test portions of the agronomic field comprises: one or more portions of the plurality of particular portions of the agronomic field having the lowest average statistical deviation are selected.